ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2024-12-18 20:27:57 +00:00
Code Issues Actions 12 Packages Projects Releases Wiki Activity

models(gallery): add hermes-3-llama-3.1-8b-lorablated (#3824)

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-10-14 10:28:56 +02:00 committed by GitHub
parent 304484c59b
commit 61388317c1
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 16 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
gallery/index.yaml
View File

@ -1496,6 +1496,22 @@
- filename: Hermes-3-Llama-3.1-70B-lorablated.Q4_K_M.gguf
sha256: 9294875ae3b8822855072b0f710ce800536d144cf303a91bcb087c4a307b578d
uri: huggingface://mradermacher/Hermes-3-Llama-3.1-70B-lorablated-GGUF/Hermes-3-Llama-3.1-70B-lorablated.Q4_K_M.gguf
- !!merge <<: *llama31
name: "hermes-3-llama-3.1-8b-lorablated"
urls:
- https://huggingface.co/mlabonne/Hermes-3-Llama-3.1-8B-lorablated-GGUF
description: |
This is an uncensored version of NousResearch/Hermes-3-Llama-3.1-8B using lorablation.
The recipe is simple:
Extraction: We extract a LoRA adapter by comparing two models: a censored Llama 3.1 (meta-llama/Meta-Llama-3-8B-Instruct) and an abliterated Llama 3.1 (mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated).
Merge: We merge this new LoRA adapter using task arithmetic to the censored NousResearch/Hermes-3-Llama-3.1-8B to abliterate it.
overrides:
parameters:
model: hermes-3-llama-3.1-8b-lorablated.Q4_K_M.gguf
files:
- filename: hermes-3-llama-3.1-8b-lorablated.Q4_K_M.gguf
sha256: 8cff9d399a0583616fe1f290da6daa091ab5c5493d0e173a8fffb45202d79417
uri: huggingface://mlabonne/Hermes-3-Llama-3.1-8B-lorablated-GGUF/hermes-3-llama-3.1-8b-lorablated.Q4_K_M.gguf
- &deepseek
## Deepseek
url: "github:mudler/LocalAI/gallery/deepseek.yaml@master"